Research & Field Notes
How attackers break voice AI agents and chat AI agents, in plain language. Research and field notes from the SottoAI team, for the people who build, secure and sign off on these agents.
undefined
Latest posts
- Interrupt the Refusal: How a Barge-In Talks Voice AI Agents Out of Saying No — A single barge-in, right as the agent starts to refuse, and harmful answers jump from 6.5% to 35.6%. The very thing that makes voice agents feel human is the thing this attack turns against it.